Explainable deep learning algorithm for distinguishing incomplete Kawasaki disease by coronary artery lesions on echocardiographic imaging

• Published in: Computer methods and programs in biomedicine Vol. 223; p. 106970
• Main Authors: Lee, Haeyun, Eun, Yongsoon, Hwang, Jae Youn, Eun, Lucy Youngmin
• Format: Journal Article
• Language: English
• Published: Ireland Elsevier B.V 01.08.2022
• Subjects: Algorithms; Child; Coronary Artery Disease - diagnostic imaging; Coronary artery lesion; Coronary Vessels - diagnostic imaging; Coronary Vessels - pathology; COVID-19 - diagnostic imaging; Deep Learning; Echocardiography; Explanable AI; Fever - complications; Fever - diagnosis; Fever - pathology; Humans; Infant; Kawasaki disease; Mucocutaneous Lymph Node Syndrome - complications; Mucocutaneous Lymph Node Syndrome - diagnostic imaging; Ultrasound Image; Deep learning; Global average pooling; Kawasaki disease; Coronavirus disease 2019; Explanable AI; Coronary artery lesion; Class activation map; Ultrasound Image; Areas under the precision-recall curve; Adaptive Moment Estimation
• ISSN: 0169-2607; 1872-7565; 1872-7565
• DOI: 10.1016/j.cmpb.2022.106970

•Performance of deep learning algorithms to diagnose the Kawasaki disease.•Deep learning could reduce the probability of misdiagnosing Kawasaki disease.•The feasibility of using a deep learning approach for detection of Kawasaki disease. Background and Objective: Incomplete Kawasaki disease (KD) has often been misdiagnosed due to a lack of the clinical manifestations of classic KD. However, it is associated with a markedly higher prevalence of coronary artery lesions. Identifying coronary artery lesions by echocardiography is important for the timely diagnosis of and favorable outcomes in KD. Moreover, similar to KD, coronavirus disease 2019, currently causing a worldwide pandemic, also manifests with fever; therefore, it is crucial at this moment that KD should be distinguished clearly among the febrile diseases in children. In this study, we aimed to validate a deep learning algorithm for classification of KD and other acute febrile diseases. Methods: We obtained coronary artery images by echocardiography of children (n = 138 for KD; n = 65 for pneumonia). We trained six deep learning networks (VGG19, Xception, ResNet50, ResNext50, SE-ResNet50, and SE-ResNext50) using the collected data. Results: SE-ResNext50 showed the best performance in terms of accuracy, specificity, and precision in the classification. SE-ResNext50 offered a precision of 81.12%, a sensitivity of 84.06%, and a specificity of 58.46%. Conclusions: The results of our study suggested that deep learning algorithms have similar performance to an experienced cardiologist in detecting coronary artery lesions to facilitate the diagnosis of KD.